Inferring typesetting board counts in early Korean metal-type printing via character-structure similarity

While movable metal-type printing in Goryeo and Joseon dynasties enabled efficient book production, certain aspects of the process remain insufficiently understood. We propose a method to estimate the number of typesetting boards used in historical metal-type printing, offering valuable insights into the scale of metal-type production at the time. Because the book title printed repeatedly on each sheet exhibits distinctive characteristics of individual typesetting boards, typesetting board counts can be inferred by clustering similar instances of the book title, implying that titles within the same cluster were printed using an identical board. To quantify the visual similarity among printed characters, we propose Character-Structure Similarity Measure (CSSM) providing robustness against variations in stroke thickness and ink spread. Experiments on seven 14th-16th century Korean metal-type books show CSSM outperforming conventional metrics in accuracy and clustering performance. This methodology contributes to historical printing studies, supporting bibliographic research, cultural heritage preservation, and digital humanities.

Authors

Institutions

Publication Details

Journal
npj Heritage Science
Published
2025-12-17
DOI
https://doi.org/10.1038/s40494-025-02251-3
Primary Topic
Handwritten Text Recognition Techniques
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Inferring typesetting board counts in early Korean metal-type printing via character-structure similarity

Kang-Sun Choi, Dong-Keun Kim
npj Heritage Science
Handwritten Text Recognition Techniques
article

Inferring typesetting board counts in early Korean metal-type printing via character-structure similarity

Kang-Sun Choi, Dong-Keun Kim
article en

Abstract

While movable metal-type printing in Goryeo and Joseon dynasties enabled efficient book production, certain aspects of the process remain insufficiently understood. We propose a method to estimate the number of typesetting boards used in historical metal-type printing, offering valuable insights into the scale of metal-type production at the time. Because the book title printed repeatedly on each sheet exhibits distinctive characteristics of individual typesetting boards, typesetting board counts can be inferred by clustering similar instances of the book title, implying that titles within the same cluster were printed using an identical board. To quantify the visual similarity among printed characters, we propose Character-Structure Similarity Measure (CSSM) providing robustness against variations in stroke thickness and ink spread. Experiments on seven 14th-16th century Korean metal-type books show CSSM outperforming conventional metrics in accuracy and clustering performance. This methodology contributes to historical printing studies, supporting bibliographic research, cultural heritage preservation, and digital humanities.

npj Heritage ScienceVol. 13(1)
Korea University of Technology and Education (KR)
National Research Foundation, National Research Foundation of Korea, Ministry of Education, India, Ministry of Science and ICT, South Korea
Openalex Percentile: Top 58%
Handwritten Text Recognition Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.